Research

19 pages, 8690 KiB

Open AccessArticle

Evaluation of Multiple Classifier Systems for Mapping Different Hierarchical Levels of Forest Ecosystems in the Mediterranean Region Using Sentinel-2, Sentinel-1, and ICESat-2 Data

by Giorgos Mallinis, Natalia Verde, Sofia Siachalou, Dionisis Latinopoulos, Christos Akratos and Ifigenia Kagalou

Forests 2023, 14(11), 2224; https://doi.org/10.3390/f14112224 - 11 Nov 2023

Viewed by 830

Abstract

The conservation and management of forest areas require knowledge about their extent and attributes on multiple scales. The combination of multiple classifiers has been proposed as an attractive classification approach for improved accuracy and robustness that can efficiently exploit the complementary nature of [...] Read more.

The conservation and management of forest areas require knowledge about their extent and attributes on multiple scales. The combination of multiple classifiers has been proposed as an attractive classification approach for improved accuracy and robustness that can efficiently exploit the complementary nature of diverse remote sensing data and the merits of individual classifiers. The aim of this study was to develop and evaluate multiple classifier systems (MCSs) within a cloud-based computing environment for multi-scale forest mapping in Northeastern Greece using passive and active remote sensing data. Five individual machine learning base classifiers were used for class discrimination across the three different hierarchy levels, and five ensemble approaches were used for combining them. In the case of the binary classification scheme in the upper level of the hierarchy for separating woody vegetation (forest and shrubs) from other land, the overall accuracy (OA) slightly increased with the use of the MCS approach, reaching 94%. At the lower hierarchical levels, when using the support vector machine (SVM) base classifier, OA reached 84.13% and 74.89% for forest type and species mapping, respectively, slightly outperforming the MCS approach. Yet, two MCS approaches demonstrated robust performance in terms of per-class accuracy, presenting the highest average F1 score across all classification experiments, indicating balanced misclassification errors across all classes. Since the competence of individual classifiers is dependent on individual scene settings and data characteristics, we suggest that the adoption of MCS systems in efficient computing environments (i.e., cloud) could alleviate the need for algorithm benchmarking for Earth’s surface cover mapping. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Graphical abstract

16 pages, 6706 KiB

Open AccessArticle

Characterization of Two Main Forest Cover Loss Transitions in North Korea from 1990 to 2020

by Yihua Jin, Jingrong Zhu, Guishan Cui, Zhenhao Yin, Weihong Zhu and Dong Kun Lee

Forests 2023, 14(10), 1966; https://doi.org/10.3390/f14101966 - 28 Sep 2023

Cited by 1 | Viewed by 881

Abstract

This study aims to characterize forest cover transitions in North Korea and identify deforested areas that are degraded or at risk of degradation. We used phenological information and random forest classifiers to perform a deforestation classification. We then extracted the two main forest [...] Read more.

This study aims to characterize forest cover transitions in North Korea and identify deforested areas that are degraded or at risk of degradation. We used phenological information and random forest classifiers to perform a deforestation classification. We then extracted the two main forest cover loss patterns, sloping farmland (farmland with slope greater than 6 degrees) and unstocked forest (crown cover less than 20%), for the years of 2000, 2010, and 2020. Based on the deforestation map of each year, we analyzed the deforestation dynamics from 1990 to 2020. Forests showed decreases in cover by 27% over the 30-year study period and accounted for 41.5% of the total land area in 2020. Deforestation spread into the core area, which led to severe shrinkage and fragmentation of forests. Unstocked forest and sloping farmland experienced the highest rates of loss among the forestland uses and accounted for 48.9% and 39.3% of the total loss over the study period, respectively. During the study period, 25,128 km², 5346 km², and 6728 km² of forestland was cleared, degraded, and was at risk of degradation or barrenness by artificial repeated fires, respectively. This methodological framework provides a valuable template for areas that are difficult to access, and the deforestation dynamics results can provide a basis for conservation and sustainable management of forest resources. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

17 pages, 19450 KiB

Open AccessArticle

Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms

by Xudong Zhang, Linfeng Yu, Quan Zhou, Dewei Wu, Lili Ren and Youqing Luo

Forests 2023, 14(9), 1889; https://doi.org/10.3390/f14091889 - 17 Sep 2023

Viewed by 850

Abstract

Mapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated the cost [...] Read more.

Mapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated the cost benefit of various combinations by mapping the species distribution of the Beijing Plain Afforestation Project with a three-level hierarchical approach. First, vegetation and non-vegetation were mapped. Then, tree crowns were extracted from the vegetation mask. Finally, Decision Tree (DT), Support Vector Machines (SVM), and Random Forest (RF) were applied to the three data sources: Pléiades-1B, WorldView-2, and Sentinel-2. The tree species classification was based on the original bands and spectral and texture indices. Sentinel-2 performed well at the stand level, with an overall accuracy of 89.29%. WorldView-2 was significantly better than Pléiades-1 at the single-tree identification level. The combination of WorldView-2 and SVM achieved the best classification result, with an overall accuracy of 90.91%. This research concludes that the low-resolution Sentinel-2 sensor can accurately map tree areas while performing satisfactorily in classifying pure forests. For mixed forests, on the other hand, WorldView-2 and Pléiades-1, which have higher resolutions, are needed for single-tree scale classification. Compared to Pléiades-1, WorldView-2 produced higher classification accuracy. In addition, this study combines algorithm comparison to provide further reference and guidance for plantation forest classification. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

17 pages, 14892 KiB

Open AccessArticle

Mapping Land Use and Land Cover Classes in São Paulo State, Southeast of Brazil, Using Landsat-8 OLI Multispectral Data and the Derived Spectral Indices and Fraction Images

by Yosio E. Shimabukuro, Egidio Arai, Gabriel M. da Silva, Tânia B. Hoffmann, Valdete Duarte, Paulo R. Martini, Andeise Cerqueira Dutra, Guilherme Mataveli, Henrique L. G. Cassol and Marcos Adami

Forests 2023, 14(8), 1669; https://doi.org/10.3390/f14081669 - 18 Aug 2023

Cited by 1 | Viewed by 1752

Abstract

This work aims to develop a new method to map Land Use and Land Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Land Imager (OLI) data. The novelty of the proposed method consists of selecting the images based on [...] Read more.

This work aims to develop a new method to map Land Use and Land Cover (LULC) classes in the São Paulo State, Brazil, using Landsat-8 Operational Land Imager (OLI) data. The novelty of the proposed method consists of selecting the images based on the spectral and temporal characteristics of the LULC classes. First, we defined the six classes to be mapped in the year 2020 as forest, forest plantation, water bodies, urban areas, agriculture, and pasture. Second, we visually analyzed their variability spectral characteristics over the year. Then, we pre-processed these images to highlight each LULC class. For the classification, the Random Forest algorithm available on the Google Earth Engine (GEE) platform was utilized individually for each LULC class. Afterward, we integrated the classified maps to create the final LULC map. The results revealed that forest areas are primarily concentrated in the eastern region of São Paulo, predominantly on steeper slopes, accounting for 19% of the study area. On the other hand, pasture and agriculture dominated 73% of all São Paulo’s landscape, reaching 39% and 34%, respectively. The overall accuracy of the classification achieved 89.10%, while producer and user accuracies were greater than 84.20% and 76.62%, respectively. To validate the results, we compared our findings with the MapBiomas Project classification, obtaining an overall accuracy of 85.47%. Therefore, our method demonstrates its potential to minimize classification errors and offers the advantage of facilitating post-classification editing for individual mapped classes. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

16 pages, 11272 KiB

Open AccessArticle

Classifying Mountain Vegetation Types Using Object-Oriented Machine Learning Methods Based on Different Feature Combinations

by Xiaoli Fu, Wenzuo Zhou, Xinyao Zhou, Feng Li and Yichen Hu

Forests 2023, 14(8), 1624; https://doi.org/10.3390/f14081624 - 11 Aug 2023

Cited by 1 | Viewed by 911

Abstract

Mountainous vegetation type classification plays a fundamental role in resource investigation in forested areas, making it necessary to accurately identify mountain vegetation types. However, Mountainous vegetation growth is readily affected by terrain and climate, which often makes interpretation difficult. This study utilizes Sentinel-2A [...] Read more.

Mountainous vegetation type classification plays a fundamental role in resource investigation in forested areas, making it necessary to accurately identify mountain vegetation types. However, Mountainous vegetation growth is readily affected by terrain and climate, which often makes interpretation difficult. This study utilizes Sentinel-2A images and object-oriented machine learning methods to map vegetation types in the complex mountainous region of Jiuzhaigou County, China, incorporating multiple auxiliary features. The results showed that the inclusion of different features improved the accuracy of mountain vegetation type classification, with terrain features, vegetation indices, and spectral features providing significant benefits. After feature selection, the accuracy of mountain vegetation type classification was further improved. The random forest recursive feature elimination (RF_RFE) algorithm outperformed the RliefF algorithm in recognizing mountain vegetation types. Extreme learning machine (ELM), random forest (RF), rotation forest (ROF), and ROF_ELM algorithms all achieved good classification performance, with an overall accuracy greater than 84.62%. Comparing the mountain vegetation type distribution maps obtained using different classifiers, we found that classification algorithms with the same base classifier ensemble exhibited similar performance. Overall, the ROF algorithm performed the best, achieving an overall accuracy of 89.68%, an average accuracy of 88.48%, and a Kappa coefficient of 0.879. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

24 pages, 6822 KiB

Open AccessArticle

A Study on Spatial Distribution Extraction of Tidal Inundated Mangroves Based on High and Low Tide Level Images

by Haotian You, Qixu You, Xu Tang, Yao Liu, Jianjun Chen and Feng Wang

Forests 2023, 14(6), 1145; https://doi.org/10.3390/f14061145 - 01 Jun 2023

Cited by 1 | Viewed by 1014

Abstract

A majority of mangroves are located in the coastal intertidal zone and are subject to tidal periodic inundation. However, the previous vegetation indices used for extracting the spatial distribution of mangroves were not able to effectively extract submerged mangroves, and the applicability of [...] Read more.

A majority of mangroves are located in the coastal intertidal zone and are subject to tidal periodic inundation. However, the previous vegetation indices used for extracting the spatial distribution of mangroves were not able to effectively extract submerged mangroves, and the applicability of the vegetation indices used on different spatial resolution images obtained from different sensors was not verified. In this study, a new vegetation index, namely the intertidal mangrove identification indices (IMIIs), was proposed, based on GF-2 images of high and low tide levels. Meanwhile, other commonly used vegetation indices were also extracted. All the vegetation indices were used to extract the spatial distribution of mangroves under tidal inundation, and applicability tests of the vegetation indices were conducted on Sentinel-2 images in three different regions. It was found that the IMIIs proposed based on GF-2 images of high and low tide levels can extract submerged mangroves relatively well, and the spatial distribution extraction results of mangroves are better than those of other vegetation indices, with IMII₂ outperforming IMII₁. At the same time, IMIIs have good applicability in medium resolution Sentinel-2 images, and there are relatively large differences in the extraction results of mangrove spatial distribution among different vegetation indices in areas with significant impact of tidal inundation. Among all vegetation indices, the extraction results of IMIIs are relatively superior. In most cases, multi variables collaborative application can improve the accuracy of mangrove spatial distribution extraction results. Based on the results of this study, it was concluded that the IMIIs proposed in this study can accurately extract the spatial distribution of mangroves inundated by tides from both medium- and high-resolution images, providing accurate basic data for effective management and scientific protection of mangrove resources. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

25 pages, 5513 KiB

Open AccessArticle

Assessing Phenological Shifts of Deciduous Forests in Turkey under Climate Change: An Assessment for Fagus orientalis with Daily MODIS Data for 19 Years

by Tuğçe Şenel, Oğuzhan Kanmaz, Filiz Bektas Balcik, Meral Avcı and H. Nüzhet Dalfes

Forests 2023, 14(2), 413; https://doi.org/10.3390/f14020413 - 17 Feb 2023

Viewed by 2408

Abstract

Understanding how natural ecosystems are and will be responding to climate change is one of the primary goals of ecological research. Plant phenology is accepted as one of the most sensitive bioindicators of climate change due to its strong interactions with climate dynamics, [...] Read more.

Understanding how natural ecosystems are and will be responding to climate change is one of the primary goals of ecological research. Plant phenology is accepted as one of the most sensitive bioindicators of climate change due to its strong interactions with climate dynamics, and a vast number of studies from all around the world present evidence considering phenological shifts as a response to climatic changes. Land surface phenology (LSP) is also a valuable tool in the absence of observational phenology data for monitoring the aforementioned shift responses. Our aim was to investigate the phenological shifts of Fagus orientalis forests in Turkey by means of daily MODIS surface reflectance data (MOD09GA) for the period between 2002 and 2020. The normalized difference vegetation index (NDVI) was calculated for the entire Turkey extent. This extent was then masked for F. orientalis. These “Fagus pixels” were then filtered by a minimum of 80% spatial and an annual 20% temporal coverage. A combination of two methods was applied to the time series for smoothing and reconstruction and the start of season (SOS), end of season, and length of season parameters were extracted. Trends in these parameters over the 19-year period were analyzed. The results were in concert with the commonly reported earlier SOS pattern, by a Sen’s slope of −0.8 days year⁻¹. Lastly, the relationships between SOS and mean, maximum and minimum temperature, growing degree days (GDD), and chilling hours (CH) were investigated. Results showed that the most significant correlations were found between the mean SOS trend and accumulated CH and accumulated GDD with a base temperature of 2 °C, both for the February–March interval. The immediate need for a phenological observation network in Turkey and its region is discussed. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

24 pages, 11742 KiB

Open AccessFeature PaperArticle

Tree Species Classification over Cloudy Mountainous Regions by Spatiotemporal Fusion and Ensemble Classifier

by Liang Cui, Shengbo Chen, Yongling Mu, Xitong Xu, Bin Zhang and Xiuying Zhao

Forests 2023, 14(1), 107; https://doi.org/10.3390/f14010107 - 05 Jan 2023

Cited by 3 | Viewed by 1267

Abstract

Accurate mapping of tree species is critical for the sustainable development of the forestry industry. However, the lack of cloud-free optical images makes it challenging to map tree species accurately in cloudy mountainous regions. In order to improve tree species identification in this [...] Read more.

Accurate mapping of tree species is critical for the sustainable development of the forestry industry. However, the lack of cloud-free optical images makes it challenging to map tree species accurately in cloudy mountainous regions. In order to improve tree species identification in this context, a classification method using spatiotemporal fusion and ensemble classifier is proposed. The applicability of three spatiotemporal fusion methods, i.e., the spatial and temporal adaptive reflectance fusion model (STARFM), the flexible spatiotemporal data fusion (FSDAF), and the spatial and temporal nonlocal filter-based fusion model (STNLFFM), in fusing MODIS and Landsat 8 images was investigated. The fusion results in Helong City show that the STNLFFM algorithm generated the best fused images. The correlation coefficients between the fusion images and actual Landsat images on May 28 and October 19 were 0.9746 and 0.9226, respectively, with an average of 0.9486. Dense Landsat-like time series at 8-day time intervals were generated using this method. This time series imagery and topography-derived features were used as predictor variables. Four machine learning methods, i.e., K-nearest neighbors (KNN), random forest (RF), artificial neural networks (ANNs), and light gradient boosting machine (LightGBM), were selected for tree species classification in Helong City, Jilin Province. An ensemble classifier combining these classifiers was constructed to further improve the accuracy. The ensemble classifier consistently achieved the highest accuracy in almost all classification scenarios, with a maximum overall accuracy improvement of approximately 3.4% compared to the best base classifier. Compared to only using a single temporal image, utilizing dense time series and the ensemble classifier can improve the classification accuracy by about 20%, and the overall accuracy reaches 84.32%. In conclusion, using spatiotemporal fusion and the ensemble classifier can significantly enhance tree species identification in cloudy mountainous areas with poor data availability. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

12 pages, 2960 KiB

Open AccessArticle

Assessment of Small-Extent Forest Fires in Semi-Arid Environment in Jordan Using Sentinel-2 and Landsat Sensors Data

by Bassam Qarallah, Yahia A. Othman, Malik Al-Ajlouni, Hadeel A. Alheyari and Bara’ah A. Qoqazeh

Forests 2023, 14(1), 41; https://doi.org/10.3390/f14010041 - 26 Dec 2022

Cited by 3 | Viewed by 1887

Abstract

The objective of this study was to evaluate the separability potential of Sentinel-2A (MultiSpectral Instrument, MSI) and Landsat (Operational Land Imager, OLI and Thermal Infrared Sensor, TIRS) derived indices for detecting small-extent (<25 ha) forest fires areas and severity degrees. Three remote sensing [...] Read more.

The objective of this study was to evaluate the separability potential of Sentinel-2A (MultiSpectral Instrument, MSI) and Landsat (Operational Land Imager, OLI and Thermal Infrared Sensor, TIRS) derived indices for detecting small-extent (<25 ha) forest fires areas and severity degrees. Three remote sensing indices [differenced Normalized Burn Ratio (dNBR), differenced Normalized Different Vegetation Index (dNDVI), and differenced surface temperature (dTST)] were used at three forest fires sites located in Northern Jordan; Ajloun (total burned area 23 ha), Dibbeen (burned area 10.5), and Sakeb (burned area 15 ha). Compared to ground reference data, Sentinel-2 MSI was able to delimit the fire perimeter more precisely than Landsat-8. The accuracy of detecting burned area (area of coincidence) in Sentinel-2 was 7%–26% higher that Landsat-8 OLI across sites. In addition, Sentinel-2 reduced the omission area by 28%–43% and the commission area by 6%–38% compared to Landsat-8 sensors. Higher accuracy in Sentinel-2 was attributed to higher spatial resolution and lower mixed pixel problem across the perimeter of burned area (mixed pixels within the fire perimeter for Sentinel-2, 8.5%–13.5% vs. 31%–52% for Landsat OLI). In addition, dNBR had higher accuracy (higher coincidence values and less omission and commission) than dNDVI and dTST. In terms of fire severity degrees, dNBR (the best fire index candidate) derived from both satellites sensors were only capable of detecting the severe spots “severely-burned” with producer accuracy >70%. In fact, the dNBR-Sentinel-2/Landsat-8 overall accuracy and Kappa coefficient for classifying fire severity degree were less than 70% across the studied sites, except for Sentinel-dNBR in Dibbeen (72.5%). In conclusion, Sentinel-dNBR and Landsat promise to delimitate forest fire perimeters of small-scale (<25 ha) areas, but further remotely-sensed techniques are require (e.g., Landsat-Sentinel data fusion) to improve the fire severity-separability potential. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

18 pages, 6177 KiB

Open AccessArticle

Mapping Secondary Vegetation of a Region of Deforestation Hotspot in the Brazilian Amazon: Performance Analysis of C- and L-Band SAR Data Acquired in the Rainy Season

by Bárbara Hass Kiyohara and Edson Eyji Sano

Forests 2022, 13(9), 1457; https://doi.org/10.3390/f13091457 - 10 Sep 2022

Cited by 1 | Viewed by 1431

Abstract

The re-suppression of secondary vegetation (SV) in the Brazilian Amazon for agriculture or land speculation occurs mostly in the rainy season. The use of optical images to monitor such re-suppression during the rainy season is limited because of the persistent cloud cover. This [...] Read more.

The re-suppression of secondary vegetation (SV) in the Brazilian Amazon for agriculture or land speculation occurs mostly in the rainy season. The use of optical images to monitor such re-suppression during the rainy season is limited because of the persistent cloud cover. This study aimed to evaluate the potential of C- and L-band SAR data acquired in the rainy season to discriminate SV in an area of new hotspot of deforestation in the municipality of Colniza, northwestern of Mato Grosso State, Brazil. This is the first time that the potential of dual-frequency SAR data was analyzed to discriminate SV, with an emphasis on data acquired during the rainy season. The L-band ALOS/PALSAR-2 and the C-band Sentinel-1 data acquired in March 2018 were processed to obtain backscattering coefficients and nine textural attributes were derived from the gray level co-occurrence matrix method (GLCM). Then, we classified the images based on the non-parametric Random Forest (RF) and Support Vector Machine (SVM) algorithms. The use of SAR textural attributes improved the discrimination capability of different LULC classes found in the study area. The results showed the best performance of ALOS/PALSAR-2 data classified by the RF algorithm to discriminate the following representative land use and land cover classes of the study area: primary forest, secondary forest, shrubby pasture, clean pasture, and bare soil, with an overall accuracy and Kappa coefficient of 84% and 0.78, respectively. The RF outperformed the SVM classifier to discriminate these five LULC classes in 14% of overall accuracy for both ALOS-2 and Sentinel-1 data sets. This study also showed that the textural attributes derived from the GLCM method are highly sensitive to the moving window size to be applied to the GLCM method. The results of this study can assist the future development of an operation system based on dual-frequency SAR data to monitor re-suppression of SV in the Brazilian Amazon or in other tropical rainforests. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

23 pages, 8108 KiB

Open AccessArticle

Discrimination of Mangrove Stages Using Multitemporal Sentinel-1 C-Band Backscatter and Sentinel-2 Data—A Case Study in Samut Songkhram Province, Thailand

by Kamonporn Upakankaew, Sarawut Ninsawat, Salvatore G. P. Virdis and Nophea Sasaki

Forests 2022, 13(9), 1433; https://doi.org/10.3390/f13091433 - 07 Sep 2022

Cited by 2 | Viewed by 1758

Abstract

Discrimination of mangrove stage changes is useful for the conservation of this valuable natural resource. However, present-day optical satellite imagery is not fully reliable due to its high sensitivity to weather conditions and tidal variables. Here, we used the Vertical Transmit—Vertical Receive Polarization [...] Read more.

Discrimination of mangrove stage changes is useful for the conservation of this valuable natural resource. However, present-day optical satellite imagery is not fully reliable due to its high sensitivity to weather conditions and tidal variables. Here, we used the Vertical Transmit—Vertical Receive Polarization (VV) and Vertical Transmit—Horizontal Receive Polarization (VH) backscatter from the same and multiple-incidence angles from Sentinel-1 SAR C-band along with Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), Normalized Difference Red Edge (

{NDVI}_{RE}

) and Chlorophyll Index Green (

{CI}_{Green}

) from the optical satellite imageries from Sentinel-2 to discriminate between the changes in disturbance, recovery, and healthy mangrove stages in Samut Songkhram province, Thailand. We found the mean NDVI values to be 0.08 (±0.11), 0.19 (±0.09), and −0.53 (±0.16) for the three stages, respectively. We further found their correlation with VH backscatter from the multiple-incidence angles at about −17.98 (±2.34), −16.43 (±1.59), and −13.40 (±1.07), respectively. The VH backscatter from multiple-incidence angles was correlated with NDVI using Pearson’s correlation (𝑟² = 0.62). However, Pearson’s correlation of a single plot (ID2) of mangrove stage change from disturbance to recovery, and then on to the healthy mangrove stage, displayed a 𝑟² of 0.93 (p value is less than 0.0001, n = 34). This indicated that the multitemporal Sentinel-1 C-band backscatter and Sentinel-2 data could be used to discriminate mangrove stages, and that a reduced correlation to significant observations was the result of variations in both optical and SAR backscatter data. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Figure 1

32 pages, 13505 KiB

Open AccessArticle

Brown Bear Food-Probability Models in West-European Russia: On the Way to the Real Resource Selection Function

by Sergey S. Ogurtsov, Anatoliy A. Khapugin, Anatoliy S. Zheltukhin, Elena B. Fedoseeva, Alexander V. Antropov, María del Mar Delgado and Vincenzo Penteriani

Forests 2022, 13(8), 1247; https://doi.org/10.3390/f13081247 - 07 Aug 2022

Cited by 2 | Viewed by 1973

Abstract

Most habitat suitability models and resource selection functions (RSFs) use indirect variables and habitat surrogates. However, it is known that in order to adequately reflect the habitat requirements of a species, it is necessary to use proximal resource variables. Direct predictors should be [...] Read more.

Most habitat suitability models and resource selection functions (RSFs) use indirect variables and habitat surrogates. However, it is known that in order to adequately reflect the habitat requirements of a species, it is necessary to use proximal resource variables. Direct predictors should be used to construct a real RSF that reflects the real influence of main resources on species habitat use. In this work, we model the spatial distribution of the main food resources of brown bear Ursus arctos L. within the natural and human-modified landscapes of the Central Forest State Nature Reserve (CFNR) for further RSF construction. Food-probability models were built for Apiaceae spp. (Angelica sylvestris L., Aegopodium podagraria L., Chaerophyllum aromaticum L.), Populus tremula L., Vaccinium myrtillus L., V. microcarpum (Turcz. ex Rupr.) Schmalh., V. oxycoccos L., Corylus avellana L., Sorbus aucuparia L., Malus domestica Borkh., anthills, xylobiont insects, social wasps and Alces alces L. using the MaxEnt algorithm. For model evaluation, we used spatial block cross-validation and held apart fully independent data. The true skill statistic (TSS) estimates ranged from 0.34 to 0.95. Distribution of Apiaceae forbs was associated with areas having rich phytomass and moist conditions on southeastern slopes. Populus tremula preferred areas with phytomass abundance on elevated sites. Vaccinium myrtillus was confined to wet boreal spruce forests. V. microcarpum and V. oxycoccos were associated with raised bogs in depressions of the terrain. Corylus avellana and Sorbus aucuparia preferred mixed forests on elevated sites. Distribution of Malus domestica was associated with meadows with dry soils in places of abandoned cultural landscapes. Anthills were common on the dry soils of meadows, and the periphery of forest areas with high illumination and low percent cover of tree canopy. Moose preferred riverine flood meadows rich in herbaceous vegetation and sparse mixed forests in spring and early summer. The territory of the human-modified CFNR buffer zone was shown to contain a higher variety of food resources than the strictly protected CFNR core area. Full article

(This article belongs to the Special Issue Mapping Forest Vegetation via Remote Sensing Tools)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Mapping Forest Vegetation via Remote Sensing Tools

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI